Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5328 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1388. Min Act: -0.0002

Data Index: 133824 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1306. Min Act: -0.0002

Data Index: 673692 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1124. Min Act: -0.0002

Data Index: 353428 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1049. Min Act: -0.0002

Data Index: 539200 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1327275 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1215111 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1040079 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0980. Min Act: -0.0002

Data Index: 83142 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0946. Min Act: -0.0002

Data Index: 30451 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1181432 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1043. Min Act: -0.0002

Data Index: 1154480 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0966. Min Act: -0.0002

Data Index: 626463 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0917. Min Act: -0.0002

Data Index: 28418 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0947. Min Act: -0.0002

Data Index: 327208 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0958. Min Act: -0.0002

Data Index: 858875 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1056786 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0912. Min Act: -0.0002

Data Index: 507279 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1091117 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0904. Min Act: -0.0002

Data Index: 586303 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0869. Min Act: -0.0002

Data Index: 667454 (C4 (Web Text))

Max Activating Token Index: 148